DETECTION OF MALARIA IN MICROSCOPIC IMAGES

Abstract

Malaria is a disease caused by bites of female mosquito. During interaction with human, the mosquitos transfer parasites genus plasmodium into human blood. Falciparum and vivax are two dangerous plasmodium, which are lethal to human. Therefore, an early detection of malaria is mandatory in order to avoid any loss of human health. Different automatic / semi-automatic malaria detection techniques have been proposed which reduces the chances of human error in prognosis of malaria. In recent years, deep learning based methods have proved their effectiveness for object detection, and therefore, it gains the attention of researchers to use it for the detection of malaria in human blood. In this paper, we are proposing a Convolutional Neural Network (CNN) model, which detects malaria in microscopic images of blood sample of human with high accuracy. The proposed model is comprised of 15 layers including 8 convolution layers with ReLu activation function, 4 max pooling layers, 1 flatten and 2 fully connected layers. The proposed method is evaluated using different statistical measures and compared with different state-of-the-art. The quantitative measures show the efficacy of the proposed model. It has 97.42% testing accuracy, 97.42% sensitivity, 97.41% specificity, 97.70% precision, 97.42% recall , 97.97% F-score , 97.41% Area Under Curve (AUC), and 94.82% Mathews correlation coefficient.